发表机构
Numberz.ai Inc.（Numberz.ai 公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究评估了一种门控感知流水线，通过结合目标检测与图像-文本比较实现带宽缩减，报告了41,977倍缩减及多次事件遗漏，并指出缩减机制与决策机制不可分离。
AI 中文摘要
在竞争链路上的机载传感器无法发送视频，因此吸引人的做法是改为发送发现结果，并报告两者之间的比率。我们评估了一条实现此功能的门控感知流水线，该流水线将学习到的目标检测和图像-文本比较与确定性调度、门控、证据积累和传输规则相结合。在语义阶段启用的分阶段录制视频上，它在211秒内发送了38,736比特，缩减了41,977倍，并命名了4个分阶段事件中的1个，且没有虚假报告。该检测结果此后已被取代：对跟踪器测量速度方式的修正移除了常态模型一直在学习的测量伪影，飞行不再升温。在修正后的代码下，该流水线在四次飞行中命名了7个分阶段事件中的1个，我们报告了这两种结果。在一次未分阶段任何内容的对照飞行中，它未报告任何内容，缩减了155,830倍：这是研究中最大的数字，但信息量最少，因为缩减比率衡量的是场景。产生缩减的机制也决定了哪些观测结果能到达决策阶段，因此两者不能分开报告。我们提供了一次飞行（3,187行）的时钟级跟踪，将三个遗漏事件中的每一个定位在其停止进展的阶段：一个未产生轨迹，一个在0.129处未通过结构位置测试，一个通过了539个结构时钟周期但仅达到3.192，而边界为3.807。我们还报告了一个已知故障模式的一个实例：在线常态模型吸收了它稍后将判断的目标，并针对该目标随后未通过的阈值进行测量。证据是四次分阶段飞行中的一次检测和六次遗漏，外加一次干净的对照，我们将其视为案例研究。我们提供了复现协议和生成的结果，指出了哪些支持工件未分发，并说明了哪些实验未运行。
英文摘要
An airborne sensor on a contested link cannot send video, so the appealing move is to send findings instead and report the ratio between the two. We evaluate a gated sensing pipeline that does this, combining learned object detection and image-text comparison with deterministic scheduling, gating, evidence accumulation and transmission rules. On staged footage with the semantic stage live it sends 38,736 bits over 211 s, a reduction of 41,977x, and names 1 of 4 staged events with no false report. That detection has since been superseded: a correction to how the tracker measures speed removed the measurement artefact the normality model had been learning from, and the flight no longer warms. Under the corrected code the pipeline names 1 of 7 staged events across four flights, and we report both. On a control flight where nothing was staged it reports nothing, a reduction of 155,830x: the largest number in the study and the least informative, because a reduction ratio measures the scene. The mechanisms that produce the reduction also decide which observations ever reach a decision, so the two cannot be reported apart. We give a tick-level trace of one flight (3,187 rows) that places each of three missed events at the stage where it stopped progressing: one produced no track, one failed the structural place test at 0.129, and one passed 539 structural ticks but reached only 3.192 against a boundary of 3.807. We also report one instance of a known failure mode, an online normality model absorbing the object it will later judge, measured against the threshold that object then failed. The evidence is one detection and six misses across four staged flights, beside one clean control, and we treat it as a case study. We give the reproduction protocol and generated results, identify which supporting artifacts are not distributed, and state which experiments did not run.
Comments13 pages, 6 tables, no figures. Reports a superseded detection result alongside the corrected run that replaces it; Table 6 carries every scored run of every staged flight
